Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection
Citations
837 citations
Cites background from "Chained Multi-stream Networks Explo..."
...Specifically, many of them have been evaluated based on the preliminary version [47] of our dataset, or pre-trained on it for transfer learning for other tasks [43], [61], [62], [63], [64], [65], [66], [67], [68], [69], [70], [71], [72], [73], [74], [75], [76], [77], [78], [79]....
[...]
809 citations
330 citations
Cites background from "Chained Multi-stream Networks Explo..."
...Most recent works on video classification are based on deep learning [6,7,8,9,10]....
[...]
...Recently, several works utilized 3D architectures for action recognition [14,10,15]....
[...]
286 citations
Cites background or methods from "Chained Multi-stream Networks Explo..."
...[48] on GT-JHMDB is solely due to an improved representation, as the approaches use the same GT pose....
[...]
...We show that this network can be trained from scratch and outperforms other pose representations [6, 48]....
[...]
...[48] proposed a pose stream that operates on semantic segmentation maps of human body parts....
[...]
...PoTion significantly outperforms their human pose stream (row ‘PoTion’ vs row ‘Pose’ of [48]) by a large margin: +14% on JHMDB and GT-JHMDB (i....
[...]
...Using a clip-level representation allows to capture long-term dependencies, in contrast to most approaches that are limited to frames [32, 43] or snippets [5, 39, 48]....
[...]
270 citations
References
49,914 citations
49,590 citations
42,067 citations
31,952 citations
"Chained Multi-stream Networks Explo..." refers background in this paper
...Many traditional works in the field of action recognition focused on designing features to discriminate action classes [19, 44, 5, 18, 17]....
[...]
28,225 citations